Fix SELU negative branch - #427
Open
andrewdalpino wants to merge 1 commit into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Fixes the SELU negative-branch derivative to use output + BETA, correcting gradient calculations.
Changes:
- Corrected SELU derivative computation.
- Updated derivative expectations and MLP regression coverage.
- Documented the fix in the changelog.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
tests/Regressors/MLPRegressorTest.php |
Exercises SELU in MLP coverage. |
tests/NeuralNet/ActivationFunctions/SELUTest.php |
Updates expected derivative values. |
src/NeuralNet/ActivationFunctions/SELU.php |
Fixes the derivative calculation. |
CHANGELOG.md |
Documents the fix. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
SELU: x≤0 → BETA·(eˣ−1), so d/dx = BETA·eˣ where BETA = SCALE·ALPHA. The correct value is (output + ALPHA)·(SCALE/SCALE)... = output + BETA. The code multiplies by SCALE again and uses ALPHA, overstating the gradient. Verified: at x=-0.5 true=1.066341 vs code=1.031268; at x=-10 true=0.00008 vs code=-0.089 (even wrong sign).